© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71618
    Prev
    Next
    INDEX
    Explanations

    actions on repeat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -3.36
    y
    -2.89
    er
    -2.77
    z
    -2.75
    {
    -2.69
    b
    -2.66
    ’
    -2.66
    的
    -2.38
    r
    -2.38
    it
    -2.36
    POSITIVE LOGITS
    ꦢ
    2.55
     podemos
    2.42
    镚
    2.33
     THEIR
    2.22
    管家
    2.19
     från
    2.13
    偲
    2.11
     از
    2.09
    罍
    2.09
    郸
    2.08
    Activations Density 0.002%

    No Known Activations